This research develops a method for synthesizing linguistic models of fuzzy systems with fuzzy input and output parameters that are described by linguistic variables. Based on the proposed method, linguistic models of the Title 1000 catalytic cracking unit for heavy residues at the Shymkent oil refinery are developed, describing the dependence of the volume and quality of gasoline on the input and operating parameters of the facility, which are fuzzy. It is substantiated that the use of a fuzzy approach, which allows the use of the experience, knowledge, and intuition (intelligence) of the decision maker and subject matter experts, is the most suitable effective method for synthesizing models of complex, fuzzily described objects and processes for comparison with other methods. The main idea of the proposed work is to solve the problems of shortage and fuzziness of initial information when developing models and optimizing the operating modes of a catalytic cracking unit through the use of knowledge, experience, and intuition of experts in this field. To solve the problems of the shortage of initial quantitative information and the fuzziness of available information when developing mathematical models, it is proposed to systematically use statistical methods, expert assessment methods, and a heuristic method based on fuzzy logic. The scientific novelty of the research lies in the development of a method for synthesizing linguistic models in a fuzzy environment and an algorithm for its implementation, which makes it possible to describe the dependence of the fuzzy values of the object’s output parameters on its fuzzy input and operating parameters. The proposed approach allows the formalization and synthesis of models of fuzzily described objects when other methods of model development are not applicable or do not give the expected results. The results of the work were simulated in the MATLAB Fuzzy Logic Toolbox.

This work reports a study into the possibility of using the GoogleNet neural network in the optoelectronic channel of the Data Fusion system. The search for the most accurate algorithms for detecting and recognizing unmanned aerial vehicles (UAVs) in Data Fusion systems has been carried out. The data processing scheme was selected (merging SVF state vectors and merging MF measurements), as well as the sensors and recognition models on each channel of the system. The Data Fusion model based on the Kalman Filter was chosen, integrating radar and optoelectronic channels. Mini-radars LPI-FMCW were used as a radar channel. Evaluation of the effectiveness of the selected Data Fusion channel model in UAV detection is based on the recognition accuracy. The main study is aimed at determining the possibility of using the GoogleNet neural network in the optoelectronic channel for UAV recognition under conditions of different range classes. The neural network for the recognition of drones was developed using transfer training technology. For training, validation, and testing of the GoogleNet neural network, a database has been built, and a special application has been developed in the MATLAB environment. The capabilities of the developed neural network were studied for 5 variants of the distance to the object. The detection objects were the Inspire 2, DJI Phantom 4 Pro, DJI F450, DU 1911 UAVs, not included in the training database. The UAV recognition accuracy by the neural network was 98.13 % at a distance of up to 5 m, 94.65 % at a distance of up to 20 m, 92.47 % at a distance of up to 20 m, 90.28 % at a distance of up to 100 m, and 88.76 % at a distance of up to 200 m. The average speed of UAV recognition by this method was 0.81 s.

This paper presents the results of mathematical models’ development for hydrotreating reactor, stripping соlumn, absorbers and hydrotreating furnace which are basic units of hydrotreating block in catalytic reforming unit. Since these objects of modeling in reforming unit of Atyrau refinery operate in conditions of insufficiency and fuzziness of the initial information, their mathematical models are developed on the basis of a systematic approach, using available information of different nature (experimental-statistical data, fuzzy information from the experts), with appropriate methods of construction for mathematical models. Mathematical models, describing the dependence of the production output from the hydrotreating reactor, columns and furnace, are designed as a nonlinear regression models based on experimental-statistical data. Whereas models, evaluating the quality indicators of generated products from the hydrotreating reactor and columns, i.e., hydrogenation, hydrogen-containing and hydrocarbon-containing gases are built based on fuzzy information from specialists-experts in the form of fuzzy multiple regression equations. We have plotted the graph for the dependence of hydrogenation products output on the temperature in the hydrotreating reactor. To describe the dependence of the optimum temperature value in hydrotreating process on raw material quality, a linguistic model is designed based on compositional rules of inference and fuzzy information. Membership functions of fuzzy parameters are constructed for linguistic models.

The rapid spread of unmanned aerial vehicles (UAVs) has created new challenges for airspace security, as drones are increasingly used for surveillance, smuggling, and potentially for attacks near critical infrastructure. A key difficulty lies in reliably distinguishing UAVs from visually similar birds in electro-optical surveillance channels, where complex backgrounds and visual noise often increase false alarms. To address this, we investigated recent YOLO architectures and developed an enhanced model named YOLOv12-ADBC, incorporating an adaptive hierarchical feature integration mechanism to strengthen multi-scale spatial fusion. This architectural refinement improves sensitivity to subtle inter-class differences between drones and birds. A dedicated dataset of 7291 images was used to train and evaluate five YOLO versions (v8–v12), together with the proposed YOLOv12-ADBC. Comparative experiments demonstrated that YOLOv12-ADBC achieved the best overall performance, with precision = 0.892, recall = 0.864, mAP50 = 0.881, mAP50–95 = 0.633, and per-class accuracy reaching 96.4% for drones and 80% for birds. In inference tests on three video sequences simulating realistic monitoring conditions, YOLOv12-ADBC consistently outperformed baselines, achieving a detection accuracy of 92.1–95.5% and confidence levels up to 88.6%, while maintaining real-time processing at 118–135 frames per second (FPS). These results demonstrate that YOLOv12-ADBC not only surpasses previous YOLO models but also offers strong potential as the optical module in multi-sensor fusion frameworks. Its integration with radar, RF, and acoustic channels is expected to further enhance system-level robustness, providing a practical pathway toward reliable UAV detection in modern airspace protection systems.

This article explores the challenges of integrating two deep learning neural networks, YOLOv5 and RT-DETR, to enhance the recognition of unmanned aerial vehicles (UAVs) within the optical-electronic channels of Sensor Fusion systems. The authors conducted an experimental study to test YOLOv5 and Faster RT-DETR in order to identify the average accuracy of UAV recognition. A dataset in the form of images of two classes of objects, UAVs, and birds, was prepared in advance. The total number of images, including augmentation, amounted to 6337. The authors implemented training, verification, and testing of the neural networks exploiting PyCharm 2024 IDE. Inference testing was conducted using six videos with UAV flights. On all test videos, RT-DETR-R50 was more accurate by an average of 18.7% in terms of average classification accuracy (Pc). In terms of operating speed, YOLOv5 was 3.4 ms more efficient. It has been established that the use of RT-DETR as the only module for UAV classification in optical-electronic detection channels is not effective due to the large volumes of calculations, which is due to the relatively large number of parameters. Based on the obtained results, an algorithm for combining two neural networks is proposed, which allows for increasing the accuracy of UAV and bird classification without significant losses in speed.